Data archiving systems rely on replication to preserve information. This paper discusses how a network of autonomousarchiving sites can trade data to achieve the most reliable replication. A series of binary trades among sites produces a peer-to-peer archiving network. Two trading algorithms are examined, one based on trading collections (even if they are different sizes) and another based on trading equal sized blocks of space (which can then store collections.) The concept of deeds is introduced; deeds track the blocks of space owned by one site at another. Policies for tuning these algorithms to provide the highest reliability, for example by changing the order in which sites are contacted and offered trades, are discussed. Finally, simulation results are presented that reveal which policies are best. The experiments indicate that a digital archive can achieve the best reliability by trading blocks of space (deeds), and that following certain policies will allow that site to maximize its reliability. Categories and Subject Descriptors: H.3.7 [Information storage and retrieval]: Digital libraries --- systems issues; E.5 [Files]: Backup/recovery General Terms: Design, reliability Additional Key Words and Phrases: data replication, fault tolerance, digital archiving, digital library, resource negotiation 1

Digital archives protect important data collections from failures by making multiple copies at other archives, so that there are always several good copies of a collection. In a cooperative replication network, sites "trade" space, so that each site contributes storage resources to the system and uses storage resources at other sites. Here, we examine bid trading: a mechanism where sites conduct auctions to determine who to trade with. A local site wishing to make a copy of a collection announces how much remote space is needed, and accepts bids for how much of its own space the local site must "pay" to acquire that remote space. We examine the best policies for determining when to call auctions and how much to bid, as well as the effects of "maverick" sites that attempt to subvert the bidding system. Simulations of auction and trading sessions indicate that bid trading can allow sites to achieve higher reliability than the alternative: a system where sites trade equal amounts of space without bidding.

1 Introduction Peer-to-peer systems form a useful architecture for awide range of important applications. Although the term "peer-to-peer " is often associated in the pub-lic imagination with Napster and related file-sharing systems, other important services that can be builton a peer-to-peer framework. For example, a group of digital libraries may cooperate with each other toprovide preservation by storing copies of each other's digital materials. In this system, each library acts asan autonomous peer in a distributed, heterogeneous collection replication mechanism. Such a commu-nity does not require a central controller to manage the replication of data; instead, each peer can com-municate with other peers to replicate its own collections. The result of individual libraries seekinglocally to preserve their own information by working with other peers is a global community in whichevery library's collections are protected.

this paper we present recent and ongoing research projects of the Peers research group at Stanford University. Section 2 studies the problems relating to locating resources in P2P systems. Section 3 discusses work on resource allocation and aggregation. Section 4 focuses on issues of resource availability and authenticity. Note, this paper should not be construed as an overview of all research problems pertaining to peer-to-peer networks. Only projects connected to our Peers group are described. Additional citations can be found in the papers referenced below

Digital archives protect important data collections from failures by making multiple copies at other archives, so that there are always several good copies of a collection. In a cooperative replication network, sites “trade ” space, so that each site contributes storage resources to the system and uses storage resources at other sites. Here, we examine bid trading: a mechanism where sites conduct auctions to determine who to trade with. A local site wishing to make a copy of a collection announces how much remote space is needed, and accepts bids for how much of its own space the local site must “pay ” to acquire that remote space. We examine the best policies for determining when to call auctions and how much to bid, as well as the effects of “maverick ” sites that attempt to subvert the bidding system. Simulations of auction and trading sessions indicate that bid trading can allow sites to achieve higher reliability than the alternative: a system where sites trade equal amounts of space without bidding.

The Internet has already established itself as one of the key information and communication media of our time. With Internet-specific types of information representation and art evolving, and with social groups forming in cyberspace, the Internet and its content is turning into an important part of our cultural heritage. This new digital cultural heritage is deemed worth preserving by an increasing number of initiatives, aiming at providing access to our contemporary Internet for future generations. Numerous challenges have to be addressed in the creation of any such archive, concerning the acquisition of data, its long term storage and preservation, as well as access provision. In this paper we provide an overview of the most prominent challenges encountered with respect to archiving the Internet and discuss possible solutions. We furthermore present a report on AOLA, the Austrian initiative of creating an on-line archive.

Digital materials can be protected from failures by replicating them at multiple autonomous, distributed sites. A Peer-to-peer Information Preservation and Exchange (PIPE) network is a good way to build a distributed replication system. A significant challenge in such networks is ensuring that documents are replicated and accessible despite malicious sites. Such sites may hinder the replication of documents in a variety of ways, including agreeing to store a copy but erasing it instead, refusing to serve a document, or serving an altered version of the document. We define a model of PIPE networks, a threat model for malicious sites, and propose basic solutions for managing these malicious sites. The basic solutions are inefficient, but demonstrate that a secure system can be built. We also sketch ways to improve the efficiency of the system.

Business to business (B2B) marketplaces are characterized by horizontal interactions across the value chain between dierent businesses. Peer-topeer (P2P) networks consisting of nodes that are peers of each other provide a suitable paradigm for implementing horizontal B2B transactions. In traditional B2B trading, most of the interactions are performed by humans. In this paper, we propose a system where buyers and sellers in a B2B marketplace employ intelligent software agents to procure items. In our system, buyer and seller agents reside on nodes connected by a peer to peer network. In order to discover sellers, a buyer agent sends out a purchase request in the form of a bid over the network. Seller agents compare the bids that they have received from buyers at certain time intervals. They then use an auction-based strategy to determine the winning bid. Our simulation results show that the number of messages exchanged in the peer to peer network is independent of the auctioning strategy used.

The Stanford Archival Repository Project aims to build a robust archiving system that can protect digital objects from failures over very long time spans. Objects are replicated among cooperating digital archives, so that if any archive fails its objects survive. We have designed an architecture for digital archives, and developed techniques for efficiently replicating objects to remote sites. We have also built simulation software that allows an archivist to design the most effective archiving system possible despite limited resources. 1

In this paper, we describe five investment streams (data storage infrastructure, knowledge management, data production control, data transport and security, and personnel skill mix) that need to be balanced against shortterm operating demands in order to maximize the probability of long-term viability of a digital library. Because of the rapid pace of information technology change, a digital library cannot be a static institution. Rather, it has to become a flexible organization adapted to continuous evolution of its infrastructure.